© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 58988
    Prev
    Next
    INDEX
    Explanations

    Beach Film Festival

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    西å®īå¸Ĥ
    -0.09
    åħ¶å®ĥéĹ®é¢ĺ
    -0.09
    iga
    -0.09
    读æĩĤ
    -0.08
    èĬ¨
    -0.08
    æĩĤå¾Ĺ
    -0.08
    ä¸Ĭä¸ĭ
    -0.08
    çļĦä¸Ģ项
    -0.08
    èµĸ以çĶŁåŃĺ
    -0.08
    ç°Į
    -0.08
    POSITIVE LOGITS
    بش
    0.08
    èĻ«
    0.08
    èŁ²
    0.08
    èĿ¼
    0.08
    ç½ķ
    0.08
     Guidance
    0.08
    ome
    0.08
    æĹłäºº
    0.08
    æľīåºıæİ¨è¿Ľ
    0.08
     Orient
    0.08
    Activations Density 0.002%

    No Known Activations